LLM EXPLORER 62,155 MODELS INDEXED

Qwen2.5 0.5B Instruct SFT V1 Tr Math Easy by erayalp

By erayalp · 7 downloads
HF Repo ↗ Copy URL

Qwen2.5 0.5B Instruct SFT V1 Tr Math Easy is an open-source language model by erayalp. Features: 0.5b LLM, VRAM: 2GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.17.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i...   Conversational   Curriculum-learning Dataset:erayalp/easy turkish m...   En   Endpoints compatible   Instruct   Math   Qwen2   Region:us   Safetensors   Supervised-fine-tuning   Tr   Turkish
Model Card on HF 🤗: https://huggingface.co/erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy 

Qwen2.5 0.5B Instruct SFT V1 Tr Math Easy Parameters and Internals

LLM NameQwen2.5 0.5B Instruct SFT V1 Tr Math Easy
Repository 🤗https://huggingface.co/erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy 
Base Model(s)  Qwen/Qwen2.5-0.5B-Instruct   Qwen/Qwen2.5-0.5B-Instruct
Model Size0.5b
Required VRAM2 GB
Updated2026-07-30
Maintainererayalp
Model Typeqwen2
Instruction-BasedYes
Model Files  2.0 GB   0.0 GB
Supported Languagestr en
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.50.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat32
Errorsreplace

Best Alternatives to Qwen2.5 0.5B Instruct SFT V1 Tr Math Easy

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 0.5B Abyme Merge3128K / 1.3 GB331
Qwen2 0.5B Abyme Merge2128K / 0.3 GB280
Qwen2.5 0.5B Instruct64K / 1 GB160
Sawyer 0.5B32K / 1 GB4743
Qwen2.5 0.5B Grounded Sft32K / 1 GB7281
Qwen2.5 0.5B Grounded Rloo32K / 1 GB7051
Qwen2.5 0.5B Instruct32K / 1 GB6324790572
Qwen2.5 0.5B Sukshma32K /  GB5871
Qwen2.5 0.5B Instruct ONNX32K /  GB3402
ZINI 1 CHAT STORIES32K / 1 GB2570
Note: green Score (e.g. "73.2") means that the model is better than erayalp/qwen2.5-0.5b-instruct-SFT-v1-tr-math-easy.